.github/workflows/daily_pipeline.yml

name: Daily GraphRAG Update Pipeline

on:
  # 토큰 요금 발생 우려 및 비용 절감을 위해 매일 자동 실행되는 스케줄(Cron)은 완벽히 주석 처리(비활성화)합니다.
  # schedule:
  #   # 매일 새벽 1시(KST) = UTC 16:00
  #   - cron: '0 16 * * *'
  # 수동 실행만 허용 (개발자님께서 필요 시 GitHub Actions 웹 UI에서 직접 가동)
  workflow_dispatch:

permissions:
  contents: write

jobs:
  update-pipeline:
    runs-on: ubuntu-latest

    steps:
      - name: Checkout Source Code
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.10'
          cache: 'pip'

      - name: Install Dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r requirements.txt

      - name: Run Scrapping & Neo4j Incremental Load
        env:
          NEO4J_URI: ${{ secrets.NEO4J_URI }}
          NEO4J_CLIENT_ID: ${{ secrets.NEO4J_CLIENT_ID }}
          NEO4J_CLIENT_SECRET: ${{ secrets.NEO4J_CLIENT_SECRET }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        run: |
          python3 src/graphBuilder/scrapping/finScrapping.py
          python3 src/graphBuilder/neo4j/finGraph.py

      - name: Commit and Push New Excel Data
        run: |
          git config --global user.name "github-actions[bot]"
          git config --global user.email "github-actions[bot]@users.noreply.github.com"
          
          # 새로 수집되어 생성된 엑셀 파일들을 스테이징
          git add src/graphBuilder/scrapping/Articles_*.xlsx
          
          # 변경사항 존재 여부 확인 후 커밋 및 푸시
          if git diff --cached --quiet; then
            echo "No new news articles found to update today."
          else
            git commit -m "chore: auto-update crawled news articles $(date +'%Y-%m-%d')"
            git push origin main
          fi